%0 Journal Article
%T 考虑气象因素和BP神经网络的中长期径流预报<br>Medium and Long Term Runoff Forecast Considering Meteorological Factors and BP Neural Network
%A 王伟
%A 金新峰
%A 尹华政
%A 刘洋
%A 余豪
%A 胡朋瑞
%J Journal of Water Resources Research
%P 391-398
%@ 2166-5982
%D 2021
%I Hans Publishing
%R 10.12677/JWRR.2021.104042
%X 中长期径流预报结果对中长期发电计划制定至关重要，为了提高中长期径流预报精度，提出了考虑气象因素与BP神经网络相结合的预报方法。首先根据偏互信息法获得影响中长期入库流量变化的关键因子，并根据模糊聚类方式对其影响径流的相关因子进行聚类分析，最后采用BP神经网络以聚类的因子为输入对中长期日平均径流进行预测。以湖南省凤滩水库为例，预测结果表明：1) BP神经网络预测模型预报效果优于支持向量基、时间序列预测模型的预报结果；2) 考虑气象因素的径流预报优于未采用气象相似相的径流预报；3) 采用气象相似性与BP神经网络相结合的径流预报效果较好，预报精度均在丙级以上。<br />
The results of medium and long-term runoff forecast are very important for medium and long-term power generation planning. In order to improve the accuracy of medium and long-term runoff forecast, a forecast method combining meteorological factors with BP neural network is proposed. Firstly, the key factors affecting the medium and long-term inflow are obtained by partial mutual information method, and the related factors affecting runoff are analyzed by fuzzy clustering method. Finally, the BP neural network is used to predict the medium and long-term daily average runoff with the clustering factors as input. Taking Fengtan reservoir in Hunan Province as an example, the prediction results show that: 1) The prediction effect of BP neural network prediction model is better than that of support vector basis and time series prediction model; 2) The runoff prediction considering meteorological factors is better than that without meteorological similarity; 3) The runoff prediction effect of combining meteorological similarity and BP neural network is better, and the prediction accuracy is in the third above grade.
%K 径流预报，中长期，BP神经网络<br>Runoff Forecast
%K Medium and Long Term
%K BP Neural Network
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=45091